Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT.
Alexandra ChronopoulouDario StojanovskiAlexander M. FraserPublished in: EMNLP (1) (2020)
Keyphrases
- language model
- statistical machine translation
- language modeling
- comparable corpora
- cross lingual
- probabilistic model
- n gram
- information retrieval
- speech recognition
- document retrieval
- context sensitive
- retrieval model
- translation model
- query expansion
- mixture model
- statistical language models
- linguistic resources
- language independent
- language model for information retrieval
- language modelling
- chinese english
- machine translation
- pseudo relevance feedback
- vector space model
- test collection
- unsupervised learning
- relevance model
- cross language retrieval
- parallel corpora
- query terms
- ad hoc information retrieval
- information retrieval systems
- machine learning
- smoothing methods
- supervised learning
- semi supervised
- multiword
- natural language processing